{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:48:41Z","timestamp":1777567721458,"version":"3.51.4"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"42","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-19139-2","type":"journal-article","created":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T12:52:08Z","timestamp":1714567928000},"page":"90271-90288","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards 360$$^{\\circ }$$ image compression for machines via modulating pixel significance"],"prefix":"10.1007","volume":"83","author":[{"given":"Silin","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0877-7143","authenticated-orcid":false,"given":"Xuelin","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiudan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,1]]},"reference":[{"issue":"9","key":"19139_CR1","doi-asserted-by":"crossref","first-page":"2316","DOI":"10.1109\/TMM.2019.2957928","volume":"22","author":"S Yang","year":"2020","unstructured":"Yang S, Zhu W, Xu H, Zhang X (2020) Graph learning based head movement prediction for interactive 360 video streaming. IEEE Trans Multimedia 22(9):2316\u20132327","journal-title":"IEEE Trans Multimedia"},{"key":"19139_CR2","doi-asserted-by":"crossref","unstructured":"Kyoungkook K, Sunghyun C (2019) Interactive and automatic navigation for 360 video playback. ACM Trans Grap 38(4):1\u201311","DOI":"10.1145\/3306346.3323046"},{"key":"19139_CR3","doi-asserted-by":"publisher","first-page":"8680","DOI":"10.1109\/TIP.2020.3016485","volume":"29","author":"L Duan","year":"2020","unstructured":"Duan L, Liu J, Yang W, Huang T, Gao W (2020) Video coding for machines: A paradigm of collaborative compression and intelligent analytics. IEEE Trans Image Process 29:8680\u20138695","journal-title":"IEEE Trans Image Process"},{"key":"19139_CR4","doi-asserted-by":"crossref","unstructured":"Yang K, Zhang J, Reiss S, Hu X, Stiefelhagen XR (2021) Capturing omni-range context for omnidirectional segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp 1376\u20131386","DOI":"10.1109\/CVPR46437.2021.00143"},{"key":"19139_CR5","doi-asserted-by":"crossref","unstructured":"Xu H, Zhao Q, Ma Y, Li X, Yuan P, Feng B, Yan C, Dai F (2022) Pandora: A panoramic detection dataset for object with orientation. In: European conference on computer vision pp 237\u2013252","DOI":"10.1007\/978-3-031-20074-8_14"},{"key":"19139_CR6","doi-asserted-by":"crossref","unstructured":"Eder M, Shvets M, Lim J, Frahm JM (2020) Tangent images for mitigating spherical distortion. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp 12426\u201312434","DOI":"10.1109\/CVPR42600.2020.01244"},{"key":"19139_CR7","unstructured":"Armeni I, Sax A, Zamir R, Silvio S (2017) Joint 2d-3d-semantic data for indoor scene understanding. arXiv preprint arXiv:1702.01105"},{"key":"19139_CR8","doi-asserted-by":"crossref","unstructured":"Chang A, Dai A, Funkhouser T, Halber M, Niessner M, Savva M, Song S, Zeng A, Zhang Y (2017) Matterport3d: Learning from rgb-d data in indoor environments. In: International conference on 3D vision pp 667\u2013676","DOI":"10.1109\/3DV.2017.00081"},{"key":"19139_CR9","unstructured":"Su Y, Grauman K (2017) Learning spherical convolution for fast features from 360 imagery. Adv Neural Inform Process Syst 30"},{"key":"19139_CR10","doi-asserted-by":"crossref","unstructured":"Su YC, Grauman K (2019) Kernel transformer networks for compact spherical convolution. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp 9442\u20139451","DOI":"10.1109\/CVPR.2019.00967"},{"key":"19139_CR11","unstructured":"Benjamin C, Paul CA, Andreas G (2018) Spherenet: Learning spherical representations for detection and classification in omnidirectional images. In: European conference on computer vision pp 62\u201378"},{"key":"19139_CR12","unstructured":"Renata K, Pascal F (2019) Geometry aware convolutional filters for omnidirectional images representation. In: International conference on machine learning pp 3351\u20133359"},{"key":"19139_CR13","doi-asserted-by":"crossref","unstructured":"Zhao Q, Zhu C, Dai F, Ma Y, Jin G, Zhang Y (2018) Distortion-aware cnns for spherical images. In: International joint conference on artificial intelligence pp 1198\u20131204","DOI":"10.24963\/ijcai.2018\/167"},{"key":"19139_CR14","unstructured":"Cohen T, Geiger M, K\u00f6hler J, Welling M (2018) Spherical CNNs. In: International conference learning representations"},{"key":"19139_CR15","unstructured":"Carlos E, Christine A, Ameesh M, Kostas D (2018) Learning SO (3) equivariant representations with spherical CNNs. In: European conference on computer vision pp 52\u201368"},{"key":"19139_CR16","doi-asserted-by":"crossref","unstructured":"Nathana\u00ebl P, Micha\u00ebl D, Tomasz K, Raphael S (2019) Deepsphere: Efficient spherical convolutional neural network with healpix sampling for cosmological applications. Astron Comput 27:130\u2013146","DOI":"10.1016\/j.ascom.2019.03.004"},{"key":"19139_CR17","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/s00041-008-9013-5","volume":"14","author":"P Kostelec","year":"2018","unstructured":"Kostelec P, Rockmore D (2018) FFTs on the rotation group. J Fourier Anal Appl 14:145\u2013179","journal-title":"J Fourier Anal Appl"},{"key":"19139_CR18","first-page":"744","volume":"43","author":"A Weinstein","year":"1996","unstructured":"Weinstein A (1996) Groupoids: unifying internal and external symmetry. Notices of the AMS 43:744\u2013752","journal-title":"Notices of the AMS"},{"key":"19139_CR19","unstructured":"Jiang C, Huang J, Karthik K, Philip M, Matthias N (2019) Spherical CNNs on unstructured grids. In: International conference on learning representation"},{"key":"19139_CR20","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","volume":"22","author":"G Sullivan","year":"2012","unstructured":"Sullivan G, Ohm J, Han W, Wiegand T (2012) Overview of the high efficiency video coding (hevc) standard. IEEE Trans Circuits Syst Video Technol 22:1649\u20131668","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"19139_CR21","unstructured":"Bross B, Chen J, Liu S, Wang Y (2020) Jvet-s2001 versatilevideo coding (draft 10). In: iJoint Video exploration team (JVET) of ITU-T SG 16 WP 3 and ISO\/IEC JTC 1\/SC 29\/WG 11"},{"key":"19139_CR22","doi-asserted-by":"crossref","unstructured":"Liu Y, Xu M, Li C, Li S, Wang Z (2017) A novel rate control scheme for panoramic video coding. In: 2017 IEEE International conference on multimedia and expo pp 691\u2013696","DOI":"10.1109\/ICME.2017.8019379"},{"key":"19139_CR23","first-page":"317","volume":"10752","author":"X Xiu","year":"2018","unstructured":"Xiu X, He Y, Ye Y (2018) An adaptive quantization method for 360-degree video coding. Applications of Digital Image Processing XLI 10752:317\u2013325","journal-title":"Applications of Digital Image Processing XLI"},{"key":"19139_CR24","doi-asserted-by":"crossref","unstructured":"Tang M, Zhang Y, Wen J, Yang S (2017) Optimized video coding for omnidirectional videos. In: 2017 IEEE International conference on multimedia and expo pp 799\u2013804","DOI":"10.1109\/ICME.2017.8019460"},{"key":"19139_CR25","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.jvcir.2018.03.001","volume":"53","author":"Y Liu","year":"2018","unstructured":"Liu Y, Yang L, Xu M, Wang Z (2018) Rate control schemes for panoramic video coding. J Vis Commun Image Represent 53:76\u201385","journal-title":"J Vis Commun Image Represent"},{"key":"19139_CR26","doi-asserted-by":"crossref","unstructured":"Li Y, Xu J, Chen Z (2017) Spherical domain rate-distortion optimization for 360-degree video coding. In: 2017 IEEE International conference on multimedia and expo pp 709\u2013714","DOI":"10.1109\/ICME.2017.8019492"},{"key":"19139_CR27","doi-asserted-by":"crossref","unstructured":"Yu M, Lakshman H, Girod B (2015) Content adaptive representations of omnidirectional videos for cinematic virtual reality. In: Proceedings of the 3rd international workshop on immersive media experiences pp 1\u20136","DOI":"10.1145\/2814347.2814348"},{"key":"19139_CR28","doi-asserted-by":"crossref","unstructured":"Youvalari R, Aminlou A, Hannuksela M (2016) Analysis of regional down-sampling methods for coding of omnidirectional video. In: 2016 Picture coding symposium (PCS) pp 1\u20135","DOI":"10.1109\/PCS.2016.7906403"},{"key":"19139_CR29","unstructured":"Boyce J, Ramasubramanian A, Skupin GSR, Tourapis A, Wang Y (2017) Hevc additional supplemental enhancement information (draft 4). Joint collaborative team on video coding of ITU-T SG 16"},{"key":"19139_CR30","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1049\/el.2017.0035","volume":"53","author":"S Lee","year":"2017","unstructured":"Lee S, Kim S, Yip E, Choi B, Song J, Ko S (2017) Omnidirectional video coding using latitude adaptive down-sampling and pixel rearrangement. Electron Lett 53:655\u2013657","journal-title":"Electron Lett"},{"key":"19139_CR31","doi-asserted-by":"crossref","unstructured":"Li M, Li J, Gu S, Wu F, Zhang D (2022) End-to-end optimized 360$$^{\\circ }$$ image compression. IEEE Trans Image Process 31:6267\u20136281","DOI":"10.1109\/TIP.2022.3208429"},{"key":"19139_CR32","unstructured":"Li M, Ma K, Li J, Zhang D (2021) Pseudocylindrical convolutions for learned omnidirectional image compression. arXiv preprint arXiv:2112.13227"},{"key":"19139_CR33","doi-asserted-by":"crossref","unstructured":"Wang X, Yu K, Dong C, Loy C (2018) Recovering realistic texture in image super-resolution by deep spatial feature transform. In: Proceedings of the IEEE conference on computer vision and pattern recognition pp 606\u2013615","DOI":"10.1109\/CVPR.2018.00070"},{"key":"19139_CR34","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) Centernet: Keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision","DOI":"10.1109\/ICCV.2019.00667"},{"key":"19139_CR35","doi-asserted-by":"crossref","unstructured":"Huang Z, Jia C, Wang S, Ma S (2021) Visual analysis motivated rate-distortion model for image coding. In: 2021 IEEE International conference on multimedia and expo (ICME) pp 1\u20136","DOI":"10.1109\/ICME51207.2021.9428417"},{"key":"19139_CR36","doi-asserted-by":"crossref","unstructured":"Choi J, Han B (2020) Task-aware quantization network for jpeg image compression. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, Proceedings, Part XX 16, pp 309\u2013324. Accessed 23\u201328 Aug 2020","DOI":"10.1007\/978-3-030-58565-5_19"},{"key":"19139_CR37","doi-asserted-by":"crossref","unstructured":"Chamain L, B\u00e9gaint FRJ, Pushparaja A, Feltman S (2021) End-to-end optimized image compression for machines, a study. In: 2021 Data compression conference (DCC) pp 163\u2013172","DOI":"10.1109\/DCC50243.2021.00024"},{"key":"19139_CR38","doi-asserted-by":"crossref","unstructured":"Le N, Zhang H, Cricri F, Ghaznavi-Youvalari R, Rahtu E (2021) Image coding for machines: an end-to-end learned approach. In: ICASSP 2021-2021 IEEE International conference on acoustics, speech and signal processing (ICASSP) pp 1590\u20131594","DOI":"10.1109\/ICASSP39728.2021.9414465"},{"key":"19139_CR39","doi-asserted-by":"crossref","unstructured":"Suzuki S, Takagi M, Hayase K, Onishi T, Shimizu A (2019) Image pre-transformation for recognition-aware image compression. In: 2019 IEEE International Conference on Image Processing (ICIP) pp 2686\u20132690","DOI":"10.1109\/ICIP.2019.8803275"},{"key":"19139_CR40","doi-asserted-by":"crossref","unstructured":"Le N, Zhang H, Cricri F, Ghaznavi R, Tavakoli H, Rahtu E (2021) Learned image coding for machines: A content-adaptive approach. In: 2021 IEEE International conference on multimedia and expo (ICME) pp 1\u20136","DOI":"10.1109\/ICME51207.2021.9428224"},{"key":"19139_CR41","doi-asserted-by":"crossref","unstructured":"Wang S, Wang S, Yang W, Zhang X, Wang S, Ma S (2021) Teacher-student learning with multi-granularity constraint towards compact facial feature representation. In: ICASSP 2021-2021 IEEE International conference on acoustics, speech and signal processing (ICASSP) pp 8503\u20138507","DOI":"10.1109\/ICASSP39728.2021.9413506"},{"key":"19139_CR42","doi-asserted-by":"publisher","first-page":"3169","DOI":"10.1109\/TMM.2021.3094300","volume":"24","author":"S Wang","year":"2021","unstructured":"Wang S, Wang S, Yang W, Zhang X, Wang S, Ma S, Gao W (2021) Towards analysis-friendly face representation with scalable feature and texture compression. IEEE Trans Multimedia 24:3169\u20133181","journal-title":"IEEE Trans Multimedia"},{"key":"19139_CR43","doi-asserted-by":"crossref","unstructured":"Zhang P, Wang S, Wang M, Li J, Wang X, Kwong S (2023) Rethinking semantic image compression: Scalable representation with cross-modality transfer. IEEE Transactions on circuits and systems for video technology 33(8)","DOI":"10.1109\/TCSVT.2023.3241225"},{"key":"19139_CR44","doi-asserted-by":"crossref","unstructured":"Chen Z, Fan K, Wang S, Duan L, Lin W, Kot A (2019) Lossy intermediate deep learning feature compression and evaluation. In: Proceedings of the 27th ACM international conference on multimedia , pp 2414\u20132422","DOI":"10.1145\/3343031.3350849"},{"key":"19139_CR45","doi-asserted-by":"publisher","first-page":"2230","DOI":"10.1109\/TIP.2019.2941660","volume":"29","author":"Z Chen","year":"2019","unstructured":"Chen Z, Fan K, Wang S, Duan L, Lin W, Kot A (2019) Toward intelligent sensing: Intermediate deep feature compression. IEEE Trans Image Process 29:2230\u20132243","journal-title":"IEEE Trans Image Process"},{"key":"19139_CR46","doi-asserted-by":"crossref","unstructured":"Raj MSAB (2020) Deriving compact feature representations via annealed contraction. In: ICASSP 2020-2020 IEEE International conference on acoustics, speech and signal processing (ICASSP) pp 2068\u20132072","DOI":"10.1109\/ICASSP40776.2020.9054527"},{"key":"19139_CR47","doi-asserted-by":"crossref","unstructured":"Singh S, Abu-El-Haija S, Johnston N, Ball\u00e9 J, Shrivastava A, Toderici G (2020) End-to-end learning of compressible features. In: 2020 IEEE International conference on image processing (ICIP) pp 3349\u20133353","DOI":"10.1109\/ICIP40778.2020.9190860"},{"key":"19139_CR48","doi-asserted-by":"crossref","unstructured":"Tateno K, Navab N, Tombari F (2018) Distortion-aware convolutional filters for dense prediction in panoramic images. In: Proceedings of the European conference on computer vision (ECCV) pp 707\u2013722","DOI":"10.1007\/978-3-030-01270-0_43"},{"key":"19139_CR49","doi-asserted-by":"crossref","unstructured":"Yang Q, Li C, Dai W, Zou J, Qi G, Xiong H (2020) Rotation equivariant graph convolutional network for spherical image classification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition pp 4303\u20134312","DOI":"10.1109\/CVPR42600.2020.00436"},{"key":"19139_CR50","first-page":"57","volume":"9970","author":"V Zakharchenko","year":"2016","unstructured":"Zakharchenko V, Choi KP, Park JH (2016) Quality metric for spherical panoramic video. Optics and Photonics for Information Processing X 9970:57\u201365","journal-title":"Optics and Photonics for Information Processing X"},{"key":"19139_CR51","doi-asserted-by":"crossref","unstructured":"Yu M, Lakshman H, Girod B (2015) A framework to evaluate omnidirectional video coding schemes. In: 2015 IEEE International symposium on mixed and augmented reality pp 31\u201336","DOI":"10.1109\/ISMAR.2015.12"},{"key":"19139_CR52","unstructured":"Ball\u00e9 J, Minnen D, Singh S, Hwang S, Johnston N (2018) Variational image compression with a scale hyperprior. arXiv preprint arXiv:1802.01436"},{"key":"19139_CR53","doi-asserted-by":"crossref","unstructured":"Song M, Choi J, Han B (2021) Variable-rate deep image compression through spatially-adaptive feature transform. In: Proceedings of the IEEE\/CVF international conference on computer vision pp 2380\u20132389","DOI":"10.1109\/ICCV48922.2021.00238"},{"key":"19139_CR54","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"19139_CR55","doi-asserted-by":"crossref","unstructured":"Dai F, Chen B, Xu H, Ma Y, Li X, Feng B, Yuan P, Yan C, Zhao Q (2022) Unbiased iou for spherical image object detection. Proceedings of the AAAI conference on artificial intelligence 36:508\u2013515","DOI":"10.1609\/aaai.v36i1.19929"},{"key":"19139_CR56","doi-asserted-by":"crossref","unstructured":"Lin T, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick C (2014) Microsoft coco: Common objects in context. In: Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, Proceedings, Part V 13 pp 740\u2013755. Accessed 6\u201312 Sept 2014","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"19139_CR57","doi-asserted-by":"crossref","unstructured":"Chou S, Sun C, Chang W, Hsu W, Sun M, Fu J (2020) 360-indoor: Towards learning real-world objects in 360$$^{\\circ }$$ indoor equirectangular images. In: 2020 IEEE Winter conference on applications of computer vision (WACV) pp 834\u2013842","DOI":"10.1109\/WACV45572.2020.9093262"},{"key":"19139_CR58","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1145\/103085.103089","volume":"34","author":"G Wallace","year":"1991","unstructured":"Wallace G (1991) The jpeg still picture compression standard. Commun ACM 34:30\u201344","journal-title":"Commun ACM"},{"key":"19139_CR59","unstructured":"Minnen D, Ball\u00e9 J, Toderici G (2018) Joint autoregressive and hierarchical priors for learned image compression. Adv Neural Inform Process Syst 31"},{"key":"19139_CR60","doi-asserted-by":"crossref","unstructured":"Liu HSJ, Katto J (2023) Learned image compression with mixed transformer-cnn architectures. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR) pp 14388\u201314397","DOI":"10.1109\/CVPR52729.2023.01383"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19139-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-19139-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19139-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T20:06:16Z","timestamp":1735416376000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-19139-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,1]]},"references-count":60,"journal-issue":{"issue":"42","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["19139"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-19139-2","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,1]]},"assertion":[{"value":"25 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 December 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 May 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No Conflicts of interests for this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}